RoboEduc: uma metodologia de aprendizado com robótica educacional

In this work, we propose a methodology for teaching robotics in elementary schools, based on the socio-historical Vygotsky theory. This methodology in conjunction with the Lego Mindstoms kit (R) and an educational software (an interface for control and programming of prototypes) are part of an educational robotics system named RoboEduc. For the practical development of this work, we have used the action-research strategy, being realized robotics activities with participation of children with age between 8 and 10 years, students of the elementary school level of Municipal School Ascendino de Almeida. This school is located at the city zone of Pitimbu, at the periphery of Natal, in Rio Grande do Norte state. The activities have focused on understanding the construction of robotic prototypes, their programming and control. At constructing prototypes, children develop zone of proximal development (ZPDs) that are learning spaces that, when well used, allow the construction not only of scientific concepts by the individuals but also of abilities and capabilities that are important for the social and cultural interactiond of each one and of the group. With the development of these practical workshops, it was possible to analyse the use of the Robot as the mediator element of the teaching-learning process and the contributions that the use of robotics may bring to teaching since elementary levels

Aprendizado por Reforço com Valores deInfluência em Sistemas Multi-Agente

We propose a new paradigm for collective learning in multi-agent systems (MAS) as a solution to the problem in which several agents acting over the same environment must learn how to perform tasks, simultaneously, based on feedbacks given by each one of the other agents. We introduce the proposed paradigm in the form of a reinforcement learning algorithm, nominating it as reinforcement learning with influence values. While learning by rewards, each agent evaluates the relation between the current state and/or action executed at this state (actual believe) together with the reward obtained after all agents that are interacting perform their actions. The reward is a result of the interference of others. The agent considers the opinions of all its colleagues in order to attempt to change the values of its states and/or actions. The idea is that the system, as a whole, must reach an equilibrium, where all agents get satisfied with the obtained results. This means that the values of the state/actions pairs match the reward obtained by each agent. This dynamical way of setting the values for states and/or actions makes this new reinforcement learning paradigm the first to include, naturally, the fact that the presence of other agents in the environment turns it a dynamical model. As a direct result, we implicitly include the internal state, the actions and the rewards obtained by all the other agents in the internal state of each agent. This makes our proposal the first complete solution to the conceptual problem that rises when applying reinforcement learning in multi-agent systems, which is caused by the difference existent between the environment and agent models. With basis on the proposed model, we create the IVQ-learning algorithm that is exhaustive tested in repetitive games with two, three and four agents and in stochastic games that need cooperation and in games that need collaboration. This algorithm shows to be a good option for obtaining solutions that guarantee convergence to the Nash optimum equilibrium in cooperative problems. Experiments performed clear shows that the proposed paradigm is theoretical and experimentally superior to the traditional approaches. Yet, with the creation of this new paradigm the set of reinforcement learning applications in MAS grows up. That is, besides the possibility of applying the algorithm in traditional learning problems in MAS, as for example coordination of tasks in multi-robot systems, it is possible to apply reinforcement learning in problems that are essentially collaborative

Modelos de dispositivos de microondas e ópticos através de redes neurais artificiais de alimentação direta

This dissertation contributes for the development of methodologies through feed forward artificial neural networks for microwave and optical devices modeling. A bibliographical revision on the applications of neuro-computational techniques in the areas of microwave/optical engineering was carried through. Characteristics of networks MLP, RBF and SFNN, as well as the strategies of supervised learning had been presented. Adjustment expressions of the networks free parameters above cited had been deduced from the gradient method. Conventional method EM-ANN was applied in the modeling of microwave passive devices and optical amplifiers. For this, they had been proposals modular configurations based in networks SFNN and RBF/MLP objectifying a bigger capacity of models generalization. As for the training of the used networks, the Rprop algorithm was applied. All the algorithms used in the attainment of the models of this dissertation had been implemented in Matlab

Predição de promotores de Bacillus subtilis usando técnicas de aprendizado de máquina

One of the most important goals of bioinformatics is the ability to identify genes in uncharacterized DNA sequences on world wide database. Gene expression on prokaryotes initiates when the RNA-polymerase enzyme interacts with DNA regions called promoters. In these regions are located the main regulatory elements of the transcription process. Despite the improvement of in vitro techniques for molecular biology analysis, characterizing and identifying a great number of promoters on a genome is a complex task. Nevertheless, the main drawback is the absence of a large set of promoters to identify conserved patterns among the species. Hence, a in silico method to predict them on any species is a challenge. Improved promoter prediction methods can be one step towards developing more reliable ab initio gene prediction methods. In this work, we present an empirical comparison of Machine Learning (ML) techniques such as Na¨ýve Bayes, Decision Trees, Support Vector Machines and Neural Networks, Voted Perceptron, PART, k-NN and and ensemble approaches (Bagging and Boosting) to the task of predicting Bacillus subtilis. In order to do so, we first built two data set of promoter and nonpromoter sequences for B. subtilis and a hybrid one. In order to evaluate of ML methods a cross-validation procedure is applied. Good results were obtained with methods of ML like SVM and Naïve Bayes using B. subtilis. However, we have not reached good results on hybrid database

Aplicação de técnicas de aprendizado de máquina no reconhecimento de classes estruturais de proteínas

Nowadays, classifying proteins in structural classes, which concerns the inference of patterns in their 3D conformation, is one of the most important open problems in Molecular Biology. The main reason for this is that the function of a protein is intrinsically related to its spatial conformation. However, such conformations are very difficult to be obtained experimentally in laboratory. Thus, this problem has drawn the attention of many researchers in Bioinformatics. Considering the great difference between the number of protein sequences already known and the number of three-dimensional structures determined experimentally, the demand of automated techniques for structural classification of proteins is very high. In this context, computational tools, especially Machine Learning (ML) techniques, have become essential to deal with this problem. In this work, ML techniques are used in the recognition of protein structural classes: Decision Trees, k-Nearest Neighbor, Naive Bayes, Support Vector Machine and Neural Networks. These methods have been chosen because they represent different paradigms of learning and have been widely used in the Bioinfornmatics literature. Aiming to obtain an improvment in the performance of these techniques (individual classifiers), homogeneous (Bagging and Boosting) and heterogeneous (Voting, Stacking and StackingC) multiclassification systems are used. Moreover, since the protein database used in this work presents the problem of imbalanced classes, artificial techniques for class balance (Undersampling Random, Tomek Links, CNN, NCL and OSS) are used to minimize such a problem. In order to evaluate the ML methods, a cross-validation procedure is applied, where the accuracy of the classifiers is measured using the mean of classification error rate, on independent test sets. These means are compared, two by two, by the hypothesis test aiming to evaluate if there is, statistically, a significant difference between them. With respect to the results obtained with the individual classifiers, Support Vector Machine presented the best accuracy. In terms of the multi-classification systems (homogeneous and heterogeneous), they showed, in general, a superior or similar performance when compared to the one achieved by the individual classifiers used - especially Boosting with Decision Tree and the StackingC with Linear Regression as meta classifier. The Voting method, despite of its simplicity, has shown to be adequate for solving the problem presented in this work. The techniques for class balance, on the other hand, have not produced a significant improvement in the global classification error. Nevertheless, the use of such techniques did improve the classification error for the minority class. In this context, the NCL technique has shown to be more appropriated

Estratégias baseadas em aprendizado para coordenação de uma frota de robôs em tarefas cooperativas

In multi-robot systems, both control architecture and work strategy represent a challenge for researchers. It is important to have a robust architecture that can be easily adapted to requirement changes. It is also important that work strategy allows robots to complete tasks efficiently, considering that robots interact directly in environments with humans. In this context, this work explores two approaches for robot soccer team coordination for cooperative tasks development. Both approaches are based on a combination of imitation learning and reinforcement learning. Thus, in the first approach was developed a control architecture, a fuzzy inference engine for recognizing situations in robot soccer games, a software for narration of robot soccer games based on the inference engine and the implementation of learning by imitation from observation and analysis of others robotic teams. Moreover, state abstraction was efficiently implemented in reinforcement learning applied to the robot soccer standard problem. Finally, reinforcement learning was implemented in a form where actions are explored only in some states (for example, states where an specialist robot system used them) differently to the traditional form, where actions have to be tested in all states. In the second approach reinforcement learning was implemented with function approximation, for which an algorithm called RBF-Sarsa($lambda$) was created. In both approaches batch reinforcement learning algorithms were implemented and imitation learning was used as a seed for reinforcement learning. Moreover, learning from robotic teams controlled by humans was explored. The proposal in this work had revealed efficient in the robot soccer standard problem and, when implemented in other robotics systems, they will allow that these robotics systems can efficiently and effectively develop assigned tasks. These approaches will give high adaptation capabilities to requirements and environment changes.

Estudo avaliativo de um algoritmo genético auto-organizável e multiobjetivo utilizando aprendizado de máquina para aplicações de telecomunicações

This paper presents an evaluative study about the effects of using a machine learning technique on the main features of a self-organizing and multiobjective genetic algorithm (GA). A typical GA can be seen as a search technique which is usually applied in problems involving no polynomial complexity. Originally, these algorithms were designed to create methods that seek acceptable solutions to problems where the global optimum is inaccessible or difficult to obtain. At first, the GAs considered only one evaluation function and a single objective optimization. Today, however, implementations that consider several optimization objectives simultaneously (multiobjective algorithms) are common, besides allowing the change of many components of the algorithm dynamically (self-organizing algorithms). At the same time, they are also common combinations of GAs with machine learning techniques to improve some of its characteristics of performance and use. In this work, a GA with a machine learning technique was analyzed and applied in a antenna design. We used a variant of bicubic interpolation technique, called 2D Spline, as machine learning technique to estimate the behavior of a dynamic fitness function, based on the knowledge obtained from a set of laboratory experiments. This fitness function is also called evaluation function and, it is responsible for determining the fitness degree of a candidate solution (individual), in relation to others in the same population. The algorithm can be applied in many areas, including in the field of telecommunications, as projects of antennas and frequency selective surfaces. In this particular work, the presented algorithm was developed to optimize the design of a microstrip antenna, usually used in wireless communication systems for application in Ultra-Wideband (UWB). The algorithm allowed the optimization of two variables of geometry antenna - the length (Ls) and width (Ws) a slit in the ground plane with respect to three objectives: radiated signal bandwidth, return loss and central frequency deviation. These two dimensions (Ws and Ls) are used as variables in three different interpolation functions, one Spline for each optimization objective, to compose a multiobjective and aggregate fitness function. The final result proposed by the algorithm was compared with the simulation program result and the measured result of a physical prototype of the antenna built in the laboratory. In the present study, the algorithm was analyzed with respect to their success degree in relation to four important characteristics of a self-organizing multiobjective GA: performance, flexibility, scalability and accuracy. At the end of the study, it was observed a time increase in algorithm execution in comparison to a common GA, due to the time required for the machine learning process. On the plus side, we notice a sensitive gain with respect to flexibility and accuracy of results, and a prosperous path that indicates directions to the algorithm to allow the optimization problems with "η" variables

Aprendizado espacial-temporal em um ambiente complexo sem restrição alimentar em ratos

Timeplace learning is the capacity of organisms to associate both space and time with a biological relevant stimulus such as food. Experiments are usually done with food restricted animals due to the belief that food system activation is necessary for timeplace learning. Another line of thought suggest that, in addition to food system activation, response cost should be increased to effectively allow timeplace discrimination. The purpose of this experiment was to test whether a complex environment, which presumably implied in a heightened response cost, would facilitate timeplace association in satiated rats using a highly palatable food as reward. Nine rats were trained in a timeplace task for 30 nonconsecutive days. A large experimental box (1x1m) divided in four compartments was used. To access each compartment the animal had to overcome a series of obstacles such as ramps, staircases and mazes. Two feeders localized in opposite compartments were rewarded with sunflower seeds in two daily sessions. One feeder offered the reward during the morning sessions while the second feeder in afternoon sessions. After the 15th day of training, the animals began to show a preference for the correct feeder during the correct time of day expressed by increased frequency of visits as well as lower latency to access the feeders. These results suggest that satiated animals are also capable of learning a timespace task as far as the experimental context is complex enough to result in a higher response cost

Investigação da relação entre conteúdo onírico e aprendizado de uma tarefa cognitiva complexa

Several lines of evidence indicate that sleep is beneficial for learning, but there is no experimental evidence yet that the content of dreams is adaptive, i.e., that dreams help the dreamer to cope with challenges of the following day. Our aim here is to investigate the role of dreams in the acquisition of a complex cognitive task. We investigated electroencephalographic recordings and dream reports of adult subjects exposed to a computer game comprising perceptual, motor, spatial, emotional and higher-level cognitive aspects (Doom). Subjects slept two nights in the sleep laboratory, a completely dark room with a comfortable bed and controlled temperature. Electroencephalographic recordings with 28 channels were continuously performed throughout the experiment to identify episodes of rapid-eye-movement (REM) sleep. Behaviors were continuously recorded in audio and video with an infrared camera. Dream reports were collected upon forced awakening from late REM sleep, and again in the morning after spontaneous awakening. On day 1, subjects were habituated to the sleep laboratory, no computer game was played, and negative controls for gamerelated dream reports were collected. On day 2, subjects played the computer game before and after sleep. Each game session lasted for an hour, and sleep for 7-9 hours. 9 different measures of performance indicated significant improve overnight. 81% of the subjects experienced intrusion of elements of the game into their dreams, including potentially adaptative strategies (insights). There was a linear correlation between performance and dream intrusion as well as for game improval and quantity of reported dreaming. In the electrophysiological analysis we mapped the subjects brain activities in different stages (SWS 1, REM 1, SWS 2, REM 2, Game 1 and Game 2), and found a modest reverberation in motor areas related to the joystick control during the sleep. When separated by gender, we found a significant difference on female subjects in the channels that indicate motor learning. Analysis of dream reports showed that the amount of gamerelated elements in dreams correlated with performance gains according to an inverted-U function analogous to the Yerkes-Dodson law that governs the relationship between arousal and learning. The results indicate that dreaming is an adaptive behavior

Criar o próprio jogo didático ou apenas jogar? Efeitos de diferentes estratégias de ensino na motivação e aprendizado de ciências

The use of games as educational tools is common, however the effectiveness of games with educational purposes is still poorly known. In this study we evaluated three different low-cost teaching strategies make and play your own board game, just play an educational science game and make a poster to be exposed in the school regarding: (1) science learning; (2) use of deep learning strategies (DLS); and (3) intrinsic motivation. We tested the hypothesis that, in these three parameters evaluated, scores would be higher in the group that made and play their own game, followed respectively by the group that just played a game and the group that made a poster. The research involved 214 fifth-grade students from six elementary schools in Natal/RN. A group of students made and played their own science board game (N = 68), a second group played a science game (N = 75), and a third group made a poster to be exposed at school (N = 71). Our hypothesis was partly empirically supported, since there was no significant difference in science learning and in the use of DLS between the group that made their own game and the group that just played the game; however, both groups had significantly higher scores in science learning and in use of DLS than the group that made the poster. There was no significant difference in the scores of intrinsic motivation among the three experimental groups. Our results indicate that activities related to non-digital games can provide a favorable context for learning in the school environment. We conclude that the use of games for educational purposes (both making a game and just playing a game) is an efficient and viable alternative to teach science in Brazilian public school

Concepções e práticas da psicologia escolar :um olhar através do estágio curricular supervisionado

School psychology can be considered a growing professional field in Brazil, in spite of the difficulties concerning both the role of the psychologists in the schools and the restrictions of the labor market. Professional training is one of the most problems faced by the area. The present study is an attempt to investigate the conceptions of school psychology and the practice of the school psychologists inside de educational agencies, from the point of view of the professional training, expressed by curricular supervised training. The reason for this choice was the important role played by supervised training in the process of professional training. To carry out this study, supervised training reports written in the 1980s and the 1990s used in the student evaluation process were examined. As the main results, we point out the co-existence during the 1980-decade of two models of psychological practice: the clinical and the educational, with the dominance of the first one. During the 1990-decade, we can observe the co-existence of the same models with the dominance (but not the hegemony) of the educational model, as shown by the activities of the students. In the 1980s, for instance, the most common activities were observation of the children (45.9%), teachers guidance (40.5%) and psychodiagnostic (37.8%). In the 1990s, the main activities were participation in staff briefings (66.6%), parents guidance (58.0%), teachers guidance (50.0%) and students counseling (41.6%). Aspects related to the importance of professional training - represented by curricular supervised training - to the professional practice are discussed

Utilizando Pesos estáticos e dinâmicos em sistemas multi-classificadores com diferentes níveis de diversidade

Although some individual techniques of supervised Machine Learning (ML), also known as classifiers, or algorithms of classification, to supply solutions that, most of the time, are considered efficient, have experimental results gotten with the use of large sets of pattern and/or that they have a expressive amount of irrelevant data or incomplete characteristic, that show a decrease in the efficiency of the precision of these techniques. In other words, such techniques can t do an recognition of patterns of an efficient form in complex problems. With the intention to get better performance and efficiency of these ML techniques, were thought about the idea to using some types of LM algorithms work jointly, thus origin to the term Multi-Classifier System (MCS). The MCS s presents, as component, different of LM algorithms, called of base classifiers, and realized a combination of results gotten for these algorithms to reach the final result. So that the MCS has a better performance that the base classifiers, the results gotten for each base classifier must present an certain diversity, in other words, a difference between the results gotten for each classifier that compose the system. It can be said that it does not make signification to have MCS s whose base classifiers have identical answers to the sames patterns. Although the MCS s present better results that the individually systems, has always the search to improve the results gotten for this type of system. Aim at this improvement and a better consistency in the results, as well as a larger diversity of the classifiers of a MCS, comes being recently searched methodologies that present as characteristic the use of weights, or confidence values. These weights can describe the importance that certain classifier supplied when associating with each pattern to a determined class. These weights still are used, in associate with the exits of the classifiers, during the process of recognition (use) of the MCS s. Exist different ways of calculating these weights and can be divided in two categories: the static weights and the dynamic weights. The first category of weights is characterizes for not having the modification of its values during the classification process, different it occurs with the second category, where the values suffers modifications during the classification process. In this work an analysis will be made to verify if the use of the weights, statics as much as dynamics, they can increase the perfomance of the MCS s in comparison with the individually systems. Moreover, will be made an analysis in the diversity gotten for the MCS s, for this mode verify if it has some relation between the use of the weights in the MCS s with different levels of diversity

Aprendizado significativo aplicado ao ensino de algoritmos

The course of Algorithms and Programming reveals as real obstacle for many students during the computer courses. The students not familiar with new ways of thinking required by the courses as well as not having certain skills required for this, encounter difficulties that sometimes result in the repetition and dropout. Faced with this problem, that survey on the problems experienced by students was conducted as a way to understand the problem and to guide solutions in trying to solve or assuage the difficulties experienced by students. In this paper a methodology to be applied in a classroom based on the concepts of Meaningful Learning of David Ausubel was described. In addition to this theory, a tool developed at UFRN, named Takkou, was used with the intent to better motivate students in algorithms classes and to exercise logical reasoning. Finally a comparative evaluation of the suggested methodology and traditional methodology was carried out, and results were discussed

Curva de aprendizado em cirurgia aórtica videolaparoscópica: estudo experimental em porcos

CONTEXTO: A cirurgia videolaparoscópica (CVL) vem evoluindo como alternativa cirúrgica menos invasiva para o tratamento da doença aterosclerótica oclusiva aorto-ilíaca e do aneurisma da aorta abdominal. Poucos estudos avaliaram objetivamente a curva de aprendizado com essa técnica em cirurgia vascular. OBJETIVO: Avaliar objetivamente os tempos e a evolução de cada passo cirúrgico e demonstrar a exeqüibilidade dessa técnica. MÉTODOS: Entre outubro 2007 e janeiro de 2008, dois cirurgiões vasculares iniciantes na CVL operaram, após cursos e treinamentos, seis porcos consecutivos, com dissecção aórtica e interposição de um enxerto de dácron em um segmento da aorta infra-renal abdominal, com técnica totalmente laparoscópica. RESULTADOS: Todos os tempos cirúrgicos foram decrescentes ao longo do estudo, apresentando redução de 45,9% no tempo total de cirurgia, 85,8% no tempo de dissecção da aorta, 81,2% na exposição da aorta, 55,1% no clampeamento total, 71% na confecção da anastomose proximal e 64,9% na anastomose distal. CONCLUSÃO: O presente estudo mostrou que os resultados técnicos satisfatórios da CVL vascular ocorreram somente após longa curva de aprendizado, que foi decrescente ao longo do tempo, à medida que aumentou a experiência e vivência com os materiais e com a visão não-estereoscópica. Essa técnica pode ser realizada com perfeição por cirurgiões vasculares desde que façam cursos especializados, com treinamento em simuladores e animais, e desde que busquem constante aprimoramento a fim de conseguir resultados similares aos obtidos com a cirurgia convencional.